首页|New Machine Learning Findings from CEA Described (Application of Machine Learnin g To Micado Passive and Active Neutron Measurement System for the Characterizati on of Radioactive Waste Drums)
New Machine Learning Findings from CEA Described (Application of Machine Learnin g To Micado Passive and Active Neutron Measurement System for the Characterizati on of Radioactive Waste Drums)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ma chine Learning. According to news originating from St. Paul les Durance, France, by NewsRx correspondents, research stated, "A passive and active neutron measur ement system has been developed within the Measurement and Instrumentation for C leaning and Decommissioning Operation (MICADO) H2020 project to estimate the nuc lear material mass inside legacy waste drums of low and intermediate radioactivi ty levels. Monte-Carlo simulations were performed to design a transportable neut ron system allowing both passive neutron coincidence counting and active interro gation with the differential die-away technique (DDT)." Financial support for this research came from Horizon 2020. Our news journalists obtained a quote from the research from CEA, "However, the calibration coefficients (CCs) representing the signal of interest (due to nucle ar material) in these two measurement modes may vary by a large amount depending on the properties of the matrix of the nuclear waste drum. Therefore, this arti cle investigates matrix effects based on 104 Monte-Carlo calculations with diffe rent waste drums, based on Taguchi experimental design with a range of densities , material compositions, filling levels, and nuclear material masses. A matrix c orrection method is studied using machine learning algorithms. The matrix effect on the neutron signal is deduced from the signal of internal neutron monitors l ocated inside the measurement cavity and from a transmission measurement with an AmBe neutron source. Those quantities can be assessed experimentally and are us ed as explanatory variables for the definition of a predictive model of the simu lated CC, either in passive or in active mode. A multilinear regression model of the CC based on ordinary least square (OLS) is built and compared to the random forest (RF) machine-learning algorithm and to the multilayer perceptron (MLP) a rtificial neural network. In passive neutron coincidence counting, the residual error of the regression is lower for the MLP and RF than for OLS. The agreement between the predicted CCs of four mockup drums used as test is better than 17% and 3%, respectively, with the MLP and RF methods, while three pred ictions are out of the 95 % confidence level range with OLS. In act ive neutron interrogation, similar conclusions are drawn. The prediction of the CC for the four mockup drums is better than 12%, 35%, and 72% for the respective MLP, RF, and OLS methods."
St. Paul les DuranceFranceEuropeCy borgsEmerging TechnologiesMachine LearningCEA
NETL
NSTL
